Invoice Splitter V1

Sample Code:

#
# Install the Python client library by running:
# pip install mindee
#

from mindee.v1 import Client, product, AsyncPredictResponse
from mindee import PathInput

# Init a new client
mindee_client = Client(api_key="my-api-key")

# Load a file from disk
input_doc = PathInput("/path/to/the/file.ext")

# Load a file from disk and enqueue it.
result: AsyncPredictResponse = mindee_client.enqueue_and_parse(
    product.InvoiceSplitterV1,
    input_doc,
)

# Print a brief summary of the parsed data
print(result.document)

class InvoiceSplitterV1(raw_prediction)

Invoice Splitter API version 1 inference prediction.

Parameters:

raw_prediction (dict[str, Any])

static get_endpoint_info(klass)

Retrieves the endpoint information for an Inference.

Should never retrieve info for CustomV1, as a custom endpoint should be created to use CustomV1.

Parameters:

klass (type[Inference]) – product subclass to access endpoint information.

Return type:

dict[str, str]

endpoint_name: str | None = 'invoice_splitter'

Name of the endpoint.

endpoint_version: str | None = '1'

Version of the endpoint.

extras: Extras | None = None

Potential Extras fields sent back along with the prediction.

is_rotation_applied: bool | None

Whether the document has had any rotation applied to it.

page_id: int | None

Optional page id for page-level predictions.

pages: list[Page[InvoiceSplitterV1Document]]

Page-level prediction(s).

prediction: InvoiceSplitterV1Document

Document-level prediction.

product: Product

Name and version of a given product, as sent back by the API.

class InvoiceSplitterV1Document(raw_prediction, page_id=None)

Invoice Splitter API version 1.4 document data.

Parameters:

• raw_prediction (dict[str, Any])

• page_id (int | None)

invoice_page_groups: list[InvoiceSplitterV1InvoicePageGroup]

List of page groups. Each group represents a single invoice within a multi-invoice document.

class InvoiceSplitterV1InvoicePageGroup(raw_prediction, page_id=None)

List of page groups. Each group represents a single invoice within a multi-invoice document.

Parameters:

• raw_prediction (dict[str, Any])

• page_id (int | None)

to_table_line()

Output in a format suitable for inclusion in an rST table.

Return type:

str

bounding_box: Quadrilateral | None

A right rectangle containing the word in the document.

confidence: float

The confidence score.

page_indexes: list[int]

List of page indexes that belong to the same invoice (group).

page_n: int

The document page on which the information was found.

polygon: Polygon

A polygon containing the word in the document.